Agentic AI: Revolutionizing Engineering in 2026

30 SEC SUMMARY

In 2026, agentic AI is reshaping engineering by enabling systems to reason across workflows, coordinate specialized agents, and deliver outcomes with minimal human intervention. Elango Somasundaram from UBS India highlights the shift towards agentic engineering, emphasizing the importance of context, guardrails, and the evolving role of developers.

TABLE OF CONTENTS

1. Introduction
2. The Evolution of AI
3. Agentic AI: The Next Frontier
4. Context as the Differentiator
5. Every Layer Counts in an Agentic System
6. The Looming Shadow of Mythos
7. Banking: A Window into the Agentic Future
8. The Changing Developer Role
9. Conclusion
10. FAQ Section

KEY HIGHLIGHTS

• Agentic AI systems coordinate specialized agents to deliver outcomes with less human intervention.
• Context and data quality are crucial for agentic AI to deliver accurate outcomes.
• Every architectural layer needs guardrails to ensure safe and reliable AI-generated workflows.
• Developers will focus more on business context, collaboration, and clear intent for AI systems.
• Banking is an early adopter of agentic AI, potentially transforming routine processes.

Introduction

In 2026, the landscape of AI development is evolving rapidly. At DevSparks Hyderabad, Elango Somasundaram, Managing Director and Chief Technology Officer of UBS India, discussed the shift towards agentic AI. This new era of AI is not just about copilots and natural language coding but about systems that can reason across workflows, coordinate specialized agents, and deliver outcomes with minimal human intervention.

The Evolution of AI

Elango traced the evolution of AI, highlighting several key shifts. From robotic process automation and cloud computing to copilots and vibe coding, AI has made significant strides. Copilots predict the next line of code, while vibe coding allows developers to build through natural language prompts. Agents can execute specific tasks, but agentic AI goes a step further by starting with intent, identifying required tasks, delegating them across specialized agents, and delivering an outcome.

Agentic AI: The Next Frontier

Elango emphasized that the next competitive advantage will depend not just on better models but on richer context, stronger guardrails, and developers who can think beyond code. Agentic AI enters the conversation by understanding the context around a task and using that context to make better decisions.

Context as the Differentiator

According to Elango, skills are quickly becoming commoditized. Most organizations now have access to powerful foundation models and specialized skills, capabilities that have been democratized through open-source ecosystems and AI/ML communities. The differentiator, he argued, is context.

For enterprises, particularly in regulated industries such as banking, context includes proprietary business processes, product knowledge, security policies, customer expectations, and organizational workflows. Generic models can write code, but they do not automatically understand how a particular bank approves transactions, how a healthcare provider manages compliance, or how an automotive company designs its products. This makes data quality foundational. Enterprises may have large amounts of information, but it is often fragmented across systems, duplicated, inconsistent, or disconnected from the workflows AI needs.

Every Layer Counts in an Agentic System

Agentic AI cannot succeed by focusing only on the application layer. Elango described enterprise architecture as a set of interconnected layers, spanning infrastructure and networking, identity management, software development practices, governance, and security.

A modern application may run across cloud and on-premises environments, connect to dozens of services, and operate within architectural principles specific to an organization. Agentic systems therefore need to reason across the wider ecosystem, rather than simply generate functional code.

Identity and access management become particularly important as agents increasingly exchange information with one another. If inaccurate or hallucinated information passes from one agent to another, the error can amplify and lead to a wrong and unintended outcome from a workflow which will have major consequences. Enterprises therefore need guardrails at every architectural layer. Connectivity, authentication, Software Development Lifecycle controls, regulatory compliance, and security policies become part of the agentic workflow rather than checks carried out at the end.

The Looming Shadow of Mythos

For enterprises, more capable reasoning models have made AI adoption both more promising and more complex. While we get a lot of efficiency in terms of developing the code faster, even testing faster, the final outcome requires thorough testing. AI can generate tens and thousands of lines of code in just a minute; we need to make sure that there is nothing wrong in it.

Earlier AI workflows relied heavily on humans validating code before it moved through testing. Agentic systems add another layer of complexity, as multiple agents could independently generate, validate, and execute different parts of a workflow. As a result, enterprises are slowing down deployment—not because the technology lacks promise, but because governance has become more important than speed.

Banking: A Window into the Agentic Future

Elango sees banking as an early example of how agentic AI could reshape operating models. Routine processes such as payment settlements, customer operations, and workflow orchestration could eventually be managed by coordinated agents rather than large operational teams.

That future, however, still depends on architects, engineers, business leaders, and operational experts designing the ecosystem behind those agents. The bigger opportunity, he argued, lies in enterprise differentiation. Every industry has a unique context that competitors cannot easily replicate. In banking, that includes regulatory knowledge, risk frameworks, payment infrastructure, and customer trust. As agentic systems mature, these contextual advantages could become more valuable than access to generic AI models.

The Changing Developer Role

Elango also addressed questions about what agentic AI means for developers. Experience still matters. An AI model may generate a thousand lines of working code, but an experienced engineer often knows how to solve the same problem more effectively and efficiently because they understand the business context, learnings from past releases, and the customer needs that aren't documented and learned via continuous interactions and refinements.

The next generation of developers will need three capabilities: understanding the business problem, collaborating across complex enterprise ecosystems, and writing clear intent for AI systems rather than simply writing code. As agentic engineering evolves, coding will become one part of the developer's toolkit. Context, judgment, and systems thinking will become increasingly important for those looking to lead with AI.

Conclusion

In 2026, agentic AI is revolutionizing engineering by enabling systems to reason across workflows, coordinate specialized agents, and deliver outcomes with minimal human intervention. The focus is shifting from how many employees use AI tools to whether AI systems can use enterprise context to deliver accurate and reliable outcomes. As enterprises navigate this new landscape, the role of developers will evolve to include understanding business context, collaborating across complex ecosystems, and writing clear intent for AI systems.

FAQ Section

What is agentic AI?

Agentic AI refers to AI systems that can reason across workflows, coordinate specialized agents, and deliver outcomes with less human intervention.

How does context impact agentic AI?

Context is crucial for agentic AI to deliver accurate outcomes. Enterprises need to provide rich context and high-quality data to ensure AI systems understand specific business processes and workflows.

What role do developers play in agentic AI?

Developers will focus on understanding business problems, collaborating across complex enterprise ecosystems, and writing clear intent for AI systems. Coding will become one part of their toolkit, with context, judgment, and systems thinking becoming increasingly important.

Call-to-Action

Ready to explore the future of AI in engineering? Visit blogy.in for more insights and updates!